CN112642022B - Infusion monitoring system and monitoring method - Google Patents
Infusion monitoring system and monitoring method Download PDFInfo
- Publication number
- CN112642022B CN112642022B CN202011623190.4A CN202011623190A CN112642022B CN 112642022 B CN112642022 B CN 112642022B CN 202011623190 A CN202011623190 A CN 202011623190A CN 112642022 B CN112642022 B CN 112642022B
- Authority
- CN
- China
- Prior art keywords
- infusion
- liquid medicine
- medicine
- height
- infusion tube
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001802 infusion Methods 0.000 title claims abstract description 191
- 238000012544 monitoring process Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 25
- 239000007788 liquid Substances 0.000 claims abstract description 135
- 239000003814 drug Substances 0.000 claims abstract description 120
- 230000008859 change Effects 0.000 claims abstract description 41
- 238000003708 edge detection Methods 0.000 claims abstract description 32
- 238000003062 neural network model Methods 0.000 claims abstract description 17
- 238000001514 detection method Methods 0.000 claims description 37
- 238000013527 convolutional neural network Methods 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 17
- 238000011176 pooling Methods 0.000 claims description 12
- 238000013500 data storage Methods 0.000 claims description 10
- 238000013528 artificial neural network Methods 0.000 abstract description 2
- 238000012546 transfer Methods 0.000 description 10
- 238000012360 testing method Methods 0.000 description 8
- 238000012549 training Methods 0.000 description 7
- 210000004369 blood Anatomy 0.000 description 4
- 239000008280 blood Substances 0.000 description 4
- 210000004204 blood vessel Anatomy 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000001960 triggered effect Effects 0.000 description 3
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 101150021123 msrA gene Proteins 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000474 nursing effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 238000002560 therapeutic procedure Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M5/00—Devices for bringing media into the body in a subcutaneous, intra-vascular or intramuscular way; Accessories therefor, e.g. filling or cleaning devices, arm-rests
- A61M5/14—Infusion devices, e.g. infusing by gravity; Blood infusion; Accessories therefor
- A61M5/168—Means for controlling media flow to the body or for metering media to the body, e.g. drip meters, counters ; Monitoring media flow to the body
- A61M5/16831—Monitoring, detecting, signalling or eliminating infusion flow anomalies
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M5/00—Devices for bringing media into the body in a subcutaneous, intra-vascular or intramuscular way; Accessories therefor, e.g. filling or cleaning devices, arm-rests
- A61M5/14—Infusion devices, e.g. infusing by gravity; Blood infusion; Accessories therefor
- A61M5/168—Means for controlling media flow to the body or for metering media to the body, e.g. drip meters, counters ; Monitoring media flow to the body
- A61M5/16831—Monitoring, detecting, signalling or eliminating infusion flow anomalies
- A61M5/1684—Monitoring, detecting, signalling or eliminating infusion flow anomalies by detecting the amount of infusate remaining, e.g. signalling end of infusion
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M5/00—Devices for bringing media into the body in a subcutaneous, intra-vascular or intramuscular way; Accessories therefor, e.g. filling or cleaning devices, arm-rests
- A61M5/14—Infusion devices, e.g. infusing by gravity; Blood infusion; Accessories therefor
- A61M5/168—Means for controlling media flow to the body or for metering media to the body, e.g. drip meters, counters ; Monitoring media flow to the body
- A61M5/16831—Monitoring, detecting, signalling or eliminating infusion flow anomalies
- A61M5/1684—Monitoring, detecting, signalling or eliminating infusion flow anomalies by detecting the amount of infusate remaining, e.g. signalling end of infusion
- A61M5/16845—Monitoring, detecting, signalling or eliminating infusion flow anomalies by detecting the amount of infusate remaining, e.g. signalling end of infusion by weight
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
- A61M2205/00—General characteristics of the apparatus
- A61M2205/18—General characteristics of the apparatus with alarm
Abstract
The invention relates to the technical field of neural network and intelligent control, in particular to an infusion monitoring system and an infusion monitoring method, wherein a camera device is adopted to monitor an infusion bottle (bag); detecting a target infusion bottle (bag) in the video image by adopting a neural network model, and detecting the height of liquid medicine in the target infusion bottle (bag) by adopting an edge detection algorithm; judging whether the height of the liquid medicine is lower than a preset reminding threshold value or not, if so, judging whether the patient needs to change the medicine or withdraw the needle according to the information of the patient in the system, and reminding the patient and informing a nurse of changing the medicine or withdrawing the needle; and judging whether the height of the liquid medicine is lower than a preset closing threshold value or not, and closing the liquid conveying pipe if the height of the liquid medicine is lower than the preset closing threshold value. The scheme can accurately monitor the amount of the traditional Chinese medicine liquid in the infusion bottle (bag), and the infusion tube is closed when a nurse fails to timely handle the liquid, so that medical accidents are avoided.
Description
Technical Field
The invention relates to the technical field of neural networks and intelligent control, in particular to an infusion monitoring system and an infusion monitoring method.
Background
In hospitals, particularly emergency departments, infusion therapy is the most common and effective treatment for patients, and the most burdensome task for nurses is to infuse the patients. A nurse can carry out nursing treatment on dozens of patients or even hundreds of patients within normal duty time, pay attention to which infusion patients need to change dressings and which patients need to pull out needles after infusion is completed at any time and any place in a high intensity manner, meanwhile, in the infusion process, family members or nurses pay attention to whether the liquid medicine in an infusion bottle (bag) is completely infused at any time so as to avoid medical accidents caused by air entering blood vessels or blood backflow due to failure of timely changing dressings or pulling out needles.
Therefore, many practitioners design a few reminding systems, for example, by setting a minimum threshold, monitoring the amount of the liquid medicine inside an infusion bottle (bag) by using a photoelectric emission tube, and reminding due to a change of a photoelectric effect when the threshold is exceeded, but in this method, a large error exists due to the fact that the surface of the liquid medicine is labeled and is shielded, the liquid is transparent, and the like, and even light may deteriorate some liquids. Many practitioners try to calculate the time required for the liquid medicine to be infused completely by calculating the remaining liquid amount and the current dropping speed through monitoring the Murphy's dropper in the infusion set, and the method has certain blindness, and accurate calculation cannot be performed when the dropping speed is too fast. Moreover, only the reminding system is arranged, which cannot help the nurse to deal with the situation that the liquid medicine in the infusion bottles (bags) of a plurality of patients is infused completely when the work is busy.
Therefore, an infusion monitoring system and an infusion monitoring method capable of solving the above technical problems are provided.
Disclosure of Invention
The invention aims to provide an infusion monitoring system and an infusion monitoring method which can accurately monitor the amount of liquid medicine in an infusion bottle (bag) and timely close an infusion tube.
The invention provides an infusion monitoring system which comprises a camera device, a server, a reminding device and an infusion tube closing device, wherein the server comprises a detection module, a judgment module and a data storage module;
the camera device is used for monitoring the infusion bottle (bag) and sending the video image to the detection module;
the detection module is used for detecting a target infusion bottle (bag) in the video image by adopting a neural network model and detecting the height of liquid medicine in the target infusion bottle (bag) by adopting an edge detection algorithm;
the judging module is used for judging whether the height of the liquid medicine is lower than a preset reminding threshold value or not, if so, judging whether the patient needs to change the medicine or pull the needle according to the patient information stored in the data storage module, and triggering the reminding device;
the reminding device is used for reminding a patient and informing a nurse of changing the medicine or pulling out the needle;
the judgment module is also used for judging whether the height of the liquid medicine is lower than a preset closing threshold value or not, and if so, triggering the liquid conveying pipe closing device;
the infusion tube closing device is used for closing the infusion tube;
and the data storage module is used for storing the patient information, the reminding threshold value and the closing threshold value.
Compared with the prior art, the scheme has the advantages that: 1. the camera device is used for monitoring the infusion bottle (bag), the neural network model is used for detecting the target infusion bottle (bag) in the video image, the edge detection algorithm is used for detecting the height of the liquid medicine in the target infusion bottle (bag), the liquid medicine in the infusion bottle (bag) can be monitored in real time, and the camera does not have any influence on the liquid medicine; the monitoring of the amount of liquid in the infusion bottle (bag) is higher in accuracy and more accurate in detection relative to the detection of the liquid, and can remind a patient and inform a nurse more timely.
2. When the nurse is informed, the nurse is also informed that the patient needs to pull out the needle or change the medicine, so that the workload of the nurse is reduced, and when the liquid medicine in the infusion bottles (bags) of a plurality of patients needs to be infused, the nurse can determine the next working sequence according to the specific condition of each patient, namely whether the patient needs to pull out the needle or change the medicine.
3. The reminding threshold value, the closing threshold value and the setting of the closing device of the infusion tube can effectively help nurses to deal with the situation that the infusion of the liquid medicine in infusion bottles (bags) of a plurality of patients is finished when the work is busy. The nurse is informed to the liquid medicine height is less than the predetermined warning threshold value, if the nurse is busy, can not in time pull out the needle or change dressings for patient, and the liquid medicine in infusion bottle (bag) continues the afterflow to when reacing the predetermined threshold value of closing, trigger transfer line closing means and close the transfer line, let the liquid in the transfer line no longer flow, prevent that the liquid medicine from transporting to the end, avoid causing the emergence of the medical accident that air admission blood vessel or blood refluence caused.
Further, the neural network model adopted by the detection module is a convolutional neural network, and the convolutional neural network is composed of two convolutional layers, two pooling layers and two full-connection layers.
Has the advantages that: the neural network model adopted by the detection module is a convolutional neural network which is composed of two convolutional layers, two pooling layers and two full-connection layers, the convolutional neural network is trained by adopting a collected data set picture, the convolutional neural network finishes training and testing, the detection accuracy of the infusion bottle (bag)/infusion bag can reach 95.6%, and the detection accuracy is ensured.
Further, the edge detection algorithm adopted by the detection module is a Canny edge detection algorithm, the horizontal straight line in the edge of the target infusion bottle (bag) detected by the Canny edge detection algorithm is selected as the real-time height of the liquid medicine level, dynamic judgment is carried out at intervals of preset time intervals according to the processing speed of the adopted processor, if all frames in the preset time intervals have dynamic changes, the straight line is judged to be the label edge if no dynamic changes exist, and the straight line is judged to be the liquid medicine level and is marked if the dynamic changes exist.
Has the advantages that: when the camera device monitors the infusion bottle (bag), the label of the infusion bottle (bag) possibly shields the liquid level height of the liquid medicine in the infusion bottle (bag), so that the detection module dynamically judges at preset interval time intervals according to the processing speed of the adopted processor, if all frames in the preset interval time have dynamic change, the straight line is judged to be the label edge if no dynamic change exists, and if the dynamic change exists, the straight line is judged to be the liquid medicine plane and is marked, and the problem that the label shields the liquid medicine in the infusion bottle (bag) is solved.
Further, if the detection module detects that a certain angle deviation exists between the position of the target infusion bottle (bag) and a camera of the camera device, the detection module performs horizontal rotation alignment processing on the picture containing the marked liquid medicine plane, and selects the middle value of the processed liquid medicine plane as the liquid medicine level.
Has the advantages that: for the plane of the liquid medicine in the target infusion bottle (bag) detected by the Canny edge detection algorithm, because the target position may have a certain angle deviation with the camera, which affects the subsequent judgment of the reminding threshold and the closing threshold, the horizontal rotation alignment processing needs to be performed on the obtained picture, so that the reminding threshold and the closing threshold cannot be triggered prematurely.
Further, the infusion tube closing device is clamped on the infusion tube and comprises a shell, an omega-shaped through hole for the infusion tube to pass through is formed in the shell, a first groove is formed in the side face of the shell, a second groove is formed in the side face of the first groove, a T-shaped reset rod and a T-shaped spring rod are arranged in the first groove, a long through hole for the infusion tube to pass through is formed in the rod portion of the T-shaped reset rod, an opening for the infusion tube to be clamped into the long through hole is formed in the side of the long through hole, the head portion of the T-shaped reset rod is located outside the shell, the bottom surface of the rod portion of the T-shaped reset rod abuts against the top surface of the head portion of the T-shaped spring rod, the bottom surface of the head portion of the T-shaped spring rod is connected with one end of a first spring, the other end of the first spring is connected with the groove of the first bottom surface, a third groove corresponding to the second groove is formed in the side face of the head portion of the T-shaped spring rod, the T-shaped limiting rod is arranged in the second groove, the head of the T-shaped limiting rod is used for limiting the extension and retraction of the T-shaped spring rod, the bottom surface of the head of the T-shaped limiting rod is connected with the second spring, the other end of the second spring is connected with the electromagnet, the electromagnet is connected with the battery and the controller, the controller is used for controlling the electric conduction of the electromagnet, and the controller is connected with the judging module of the server.
Has the advantages that: the infusion tube closing device can close the infusion tube, stop the flow of liquid in the infusion tube, recycle the infusion tube and save the use cost.
The basic scheme provided by the invention is as follows: an infusion monitoring method comprises the following steps:
s1, monitoring the infusion bottle (bag) by a camera device;
s2, detecting a target infusion bottle (bag) in the video image by adopting a neural network model, and detecting the liquid medicine height in the target infusion bottle (bag) by adopting an edge detection algorithm;
s3, judging whether the height of the liquid medicine is lower than a preset reminding threshold value, if so, judging whether the patient needs to change the medicine or pull the needle according to the information of the patient in the system, and reminding the patient and informing a nurse to change the medicine or pull the needle;
and S4, judging whether the height of the liquid medicine is lower than a preset closing threshold value, and if the height of the liquid medicine is lower than the preset closing threshold value, triggering a closing device of the infusion tube to close the infusion tube.
Compared with the prior art, the scheme has the advantages that: 1. the camera device is used for monitoring the infusion bottle (bag), the neural network model is used for detecting the target infusion bottle (bag) in the video image, the edge detection algorithm is used for detecting the height of the liquid medicine in the target infusion bottle (bag), the liquid medicine in the infusion bottle (bag) can be monitored in real time, and the camera does not have any influence on the liquid medicine; the monitoring of the amount of liquid in the infusion bottle (bag) is higher in accuracy and more accurate in detection relative to the detection of the liquid, and can remind a patient and inform a nurse more timely.
2. When the nurse is informed, the nurse is also informed that the patient needs to pull out the needle or change the medicine, so that the workload of the nurse is reduced, and when the liquid medicine in the infusion bottles (bags) of a plurality of patients needs to be infused, the nurse can determine the next working sequence according to the specific condition of each patient, namely whether the patient needs to pull out the needle or change the medicine.
3. The reminding threshold value, the closing threshold value and the setting of the infusion tube closing device can effectively help nurses to deal with the situation that the infusion of the liquid medicine in infusion bottles (bags) of a plurality of patients is finished when the work is busy. The nurse is informed to the liquid medicine height is less than the predetermined warning threshold value, if the nurse is busy, can not in time pull out the needle or change dressings for patient, and the liquid medicine in infusion bottle (bag) continues the afterflow to when reacing the predetermined threshold value of closing, trigger transfer line closing means and close the transfer line, let the liquid in the transfer line no longer flow, prevent that the liquid medicine from transporting to the end, avoid causing the emergence of the medical accident that air admission blood vessel or blood refluence caused.
Further, the neural network model is a convolutional neural network, and the convolutional neural network is composed of two convolutional layers, two pooling layers and two full-connection layers.
Has the advantages that: the convolutional neural network is composed of two convolutional layers, two pooling layers and two full-connection layers, the convolutional neural network is trained by adopting collected data set pictures, the convolutional neural network completes training and testing, the detection accuracy of an infusion bottle (bag)/an infusion bag can reach 95.6%, and the detection accuracy is guaranteed.
Further, in S2, the edge detection algorithm adopted is a Canny edge detection algorithm, the horizontal straight line in the edge of the target infusion bottle (bag) detected by the Canny edge detection algorithm is selected as the real-time height of the liquid level of the drug, dynamic judgment is performed at preset intervals according to the processing speed of the processor adopted, if there is dynamic change in all frames within the preset intervals, the straight line is determined to be the label edge if there is no dynamic change, and the straight line is determined to be the liquid level and marked if there is dynamic change.
Has the beneficial effects that: when the camera device monitors the infusion bottle (bag), the label of the infusion bottle (bag) possibly shields the liquid level height of the liquid medicine in the infusion bottle (bag), so that dynamic judgment is carried out at preset interval time according to the processing speed of an adopted processor, if dynamic change exists in all frames in the preset interval time, whether the straight line has dynamic change or not is judged, if no dynamic change exists, the straight line is judged to be the label edge, if dynamic change exists, the straight line is judged to be the liquid medicine plane and is marked, and the problem that the label shields the liquid medicine in the infusion bottle (bag) is solved.
Further, if a certain angle deviation exists between the position of the target infusion bottle (bag) and a camera of the camera device, the picture containing the marked liquid medicine plane is subjected to horizontal rotation alignment processing, and the middle value of the processed liquid medicine plane is selected as the liquid medicine level.
Has the advantages that: for the plane of the liquid medicine in the target infusion bottle (bag) detected by the Canny edge detection algorithm, because the target position may have a certain angle deviation with the camera to influence the subsequent judgment of the reminding threshold and the closing threshold, the horizontal rotation alignment processing needs to be performed on the obtained picture, so that the reminding threshold and the closing threshold cannot be triggered prematurely.
Furthermore, the infusion tube closing device is clamped on the infusion tube through an omega-shaped through hole arranged on the device, and the infusion tube closing device clamps the infusion tube after receiving a closing signal.
Has the advantages that: the infusion tube closing device is clamped on the infusion tube through the omega-shaped through hole arranged on the device, the infusion tube closing device clamps the infusion tube after receiving a closing signal, the liquid medicine in the infusion tube is stopped from flowing, and medical accidents are prevented.
Drawings
FIG. 1 is a schematic diagram of an infusion monitoring system in accordance with one embodiment;
FIG. 2 is a top view of an infusion tube closing device of an infusion monitoring system in accordance with one embodiment;
FIG. 3 is an elevational, cross-sectional view of an infusion tube closing device of an infusion monitoring system in accordance with one embodiment;
FIG. 4 is a top cross-sectional view of an infusion tube closing device of an infusion monitoring system in accordance with one embodiment;
FIG. 5 is a flowchart of a method for monitoring an infusion according to a second embodiment;
FIG. 6 is a schematic diagram of a model of a trained convolutional neural network for an infusion monitoring method according to a second embodiment;
FIG. 7 is a schematic diagram illustrating the testing results of the dark-color edge detection algorithm in the infusion monitoring method according to the second embodiment;
FIG. 8 is a schematic diagram illustrating the testing results of the transparent liquid medicine edge detection algorithm in the infusion monitoring method according to the second embodiment;
FIG. 9 is a schematic plan view of a correction solution for an infusion monitoring method according to the second embodiment.
Detailed Description
Reference numerals in the drawings of the specification include: the device comprises a shell 1, an omega-shaped through hole 2, a T-shaped reset rod 3, a T-shaped spring rod 4, a long through hole 5, a first spring 6, a third groove 7, a T-shaped limiting rod 8, a second spring 9, an electromagnet 10, a battery 11 and a controller 12.
Example one
The embodiment is basically as shown in the attached figure 1: the utility model provides an infusion monitored control system, includes camera device, server, reminding device, transfer line closing device, the server includes detection module, judgement module and data storage module.
The camera device is used for monitoring an infusion bottle (bag) and sending a video image to the detection module; the camera device adopts an IP camera.
The detection module is used for detecting a target infusion bottle (bag) in the video image by adopting a neural network model and detecting the liquid medicine height in the target infusion bottle (bag) by adopting an edge detection algorithm; the neural network model is a convolutional neural network, and the convolutional neural network is composed of two convolutional layers, two pooling layers and two full-connection layers; the edge detection algorithm is a Canny edge detection algorithm, a horizontal straight line in the edge of a target infusion bottle (bag) detected by the Canny edge detection algorithm is selected as the real-time height of the liquid level of the medicine, dynamic judgment is carried out at intervals of preset interval time according to the processing speed of an adopted processor, if all frames in the preset interval time have dynamic change, the straight line is judged to be the edge of a label if the dynamic change does not exist, and the straight line is judged to be the plane of the medicine liquid and is marked if the dynamic change exists, so that the problem that the label blocks the medicine liquid in the infusion bottle (bag) is solved; the detection module is also used for detecting whether the picture of the marked liquid medicine plane is inclined because of certain angle deviation between the position of a target infusion bottle (bag) and a camera of the camera device, carrying out horizontal rotation alignment processing on the picture of the marked liquid medicine plane, and selecting the middle value of the processed liquid medicine plane as the liquid medicine liquid level, so that the liquid medicine liquid level cannot trigger a reminding threshold value and a closing threshold value too early.
The judging module is used for judging whether the height of the liquid medicine is lower than a preset reminding threshold value or not, if so, judging whether the patient needs to change the medicine or pull the needle according to the patient information stored in the data storage module, and triggering the reminding device.
The reminding device is used for reminding a patient and informing a nurse of changing the medicine or pulling the needle; the reminding device comprises a voice player arranged beside the hospital bed, a display screen arranged at the nurse station and a voice player.
The judgment module is also used for judging whether the height of the liquid medicine is lower than a preset closing threshold value or not, and if so, triggering the closing device of the infusion tube.
And the data storage module is used for storing the patient information, the reminding threshold value and the closing threshold value. The stored patient information may be obtained by the server in connection with the hospital system, so that the reminder threshold and the shutdown threshold may be set by the network connection server.
The infusion tube closing device is used for closing the infusion tube; the infusion tube closing device is clamped on an infusion tube, as shown in figure 2, the infusion tube closing device comprises a shell 1, an omega-shaped through hole 2 for the infusion tube to pass through is formed in the shell 1, as shown in figure 3, a first groove is formed in the side face of the shell 1, a second groove is formed in the side face of the first groove, a T-shaped reset rod 3 and a T-shaped spring rod 4 are arranged in the first groove, a long through hole 5 for the infusion tube to pass through is formed in the rod portion of the T-shaped reset rod 3, an opening for the infusion tube to be clamped into the long through hole 5 is formed in the side of the long through hole 5, the head of the T-shaped reset rod 3 is located outside the shell 1, the bottom surface of the rod portion of the T-shaped reset rod 3 abuts against the top surface of the head of the T-shaped spring rod 4, the bottom surface of the head of the T-shaped spring rod 4 is connected with one end of a first spring 6, and the other end of the first spring 6 is connected with the bottom surface of the first groove, as shown in fig. 4, a third groove 7 corresponding to the second groove is formed in the side face of the head of the T-shaped spring rod 4, a T-shaped limiting rod 8 is arranged in the second groove, the head of the T-shaped limiting rod 8 is used for limiting the extension and retraction of the T-shaped spring rod 4, the bottom face of the head of the T-shaped limiting rod 8 is connected with a second spring 9, the other end of the second spring 9 is connected with an electromagnet 10, the electromagnet 10 is connected with a battery 11 and a controller 12, the controller 12 is used for controlling the electric conduction of the electromagnet 10, and the controller 12 is connected with a judgment module of a server through a network.
The specific use is as follows: the infusion tube closing device is clamped on the infusion tube through the omega-shaped through hole 2, the head of the T-shaped limiting rod 8 is clamped into the third groove 7 of the T-shaped spring rod 4 under the action of the elastic force of the second spring 9, the first spring 6 on the bottom surface of the head of the T-shaped spring rod 4 is compressed, the bottom surface of the rod part of the T-shaped reset rod 3 is abutted to the top surface of the head of the T-shaped spring rod 4, and the infusion tube is positioned in the long through hole 5.
IP camera control infusion bottle (bag), and send video image for detection module, detection module adopts neural network model detection video image's target infusion bottle (bag), adopt edge detection algorithm detection target infusion bottle (bag) liquid medicine height, judge whether the liquid medicine height is less than predetermined warning threshold value, if be less than, then judge this patient according to the patient information of storage in the data storage module and need change dressings or pull out the needle, and trigger reminding device, the pronunciation player broadcast that sets up promptly beside the sick bed reminds pronunciation and reminds patient, the display screen that sets up at nurse station shows patient information, the patient demand is broadcast to the pronunciation player.
If the nurse cannot come in time and the liquid in the infusion bottle continues to flow, the judgment module judges whether the liquid medicine height is lower than a preset closing threshold value, and if so, a closing signal is sent to the controller 12 of the infusion closing device. When the controller 12 receives a closing signal sent by a judgment module of the server, the controller 12 controls the electromagnet 10 to conduct electricity, the electromagnet 10 conducts electricity for a period of time, the electromagnet 10 is ensured to attract the T-shaped limiting rod 8 to approach the T-shaped limiting rod 8, the T-shaped limiting rod 8 compresses the second spring 9, the head of the T-shaped limiting rod 8 leaves the third groove 7 of the T-shaped spring rod 4, the T-shaped spring rod 4 is subjected to the elastic force of the first spring 6, the T-shaped reset rod 3 is pushed, the T-shaped reset rod 3 drives the infusion tube, the infusion tube is crushed and clamped, and then liquid in the infusion tube stops flowing. When needing to restore, press the head of T type release link 3, promote T type release link 3, T type release link 3 promotes T type spring beam 4, and first spring 6 of T type spring beam 4 compression, T type gag lever post 8 receive the elasticity of second spring 9, block in third recess 7.
Example two
The second embodiment is substantially as shown in figure 5: an infusion monitoring method comprises the following steps:
s1, monitoring the infusion bottle (bag) by a camera device; the camera device adopted in the embodiment is a network camera;
s2, detecting a target infusion bottle (bag) in the video image by adopting a neural network model, and detecting the liquid medicine height in the target infusion bottle (bag) by adopting an edge detection algorithm;
as shown in fig. 6, the neural network model is a convolutional neural network, and the convolutional neural network is composed of two convolutional layers, two pooling layers, and two fully-connected layers. The picture input by the convolutional neural network is 112 × 112pixels, and the specific design content is as follows:
(1) the pictures in the training set such as the input label data set enter the 1 st convolution layer C1 in 3 channels, wherein 32 convolution kernels are used, 3 x 3pixels with the highest size selection efficiency are selected, and 32 feature maps with the size of 565 x 56pixels are generated;
(2) carrying out dimensionality reduction on the feature map in the step (1) through a pooling layer S2, and selecting an ave-pooling with the size of 2 × 2pixels to obtain 32 feature maps with the size of 28 × 28 pixels;
(3) the feature map of step (2) enters a second convolutional layer C3 for further feature extraction, wherein 64 convolutional kernels are used, the size is 3 × 3pixels, and 64 feature maps with the size of 14 × 14pixels are generated;
(4) carrying out dimension reduction treatment on the feature maps in the step (3) through a pooling layer S4, wherein the ave-pooling with the size of 2 x 2pixels is selected to obtain 64 feature maps with the size of 7 x 7 pixels;
(5) and (5) the feature map in the step (4) respectively passes through full connection layers F6 and F7 with neuron sizes of 512 and 256, and outputs of the pictures are classified into two categories by using a Softmax function: an infusion bottle or an infusion bag.
20000 pictures are adopted to train the convolutional neural network, the pictures mainly come from hospital clinical pictures, due to limited resources and large required training amount, the operations of turning, rotating, locally compressing, target expanding, target partially shielding and the like are carried out on part of the obtained and marked target pictures, the universality is expanded, the batch compression is carried out on the target pictures, the size is 112 multiplied by 112, 17000 pictures in total are selected for training, and 3000 pictures in total are selected for testing in the remaining 15%.
The contents of the convolutional neural network parameters and the initialization design are as follows:
the convolutional neural network initializes all convolutional layer parameters by using an 'Msra' method, iteration is performed by using a random gradient descent (SGD) method, batch standardization (BN, the size of 32) is used for accelerating the convergence rate, the initialized learning rate is 0.1, the attenuation factor is 0.0001, and the impulse is 0.9, after iteration, the network completes training and testing, and the detection accuracy of an infusion bottle/an infusion bag can reach 95.6%. The effect of accurately identifying the target infusion bottle (bag) can be achieved. The test results are obtained by training and testing the convolutional neural network under the hardware conditions of the following table.
In the step S2, the adopted edge detection algorithm is a Canny edge detection algorithm, the edge of the target infusion bottle (bag) detected by the Canny edge detection algorithm is selected as a horizontal straight line therein as a real-time height of the liquid level of the liquid medicine, and dynamic judgment is performed at preset intervals according to a processing speed of an adopted processor, if there is a dynamic change in all frames within the preset intervals, the straight line is judged to be a label edge if there is no dynamic change, and the straight line is judged to be the liquid level and marked if there is a dynamic change. And if a certain angle deviation exists between the position of the target infusion bottle (bag) and a camera of the camera device, carrying out horizontal rotation alignment processing on the picture containing the marked liquid medicine plane, and selecting the middle value of the processed liquid medicine plane as the liquid medicine level. The specific contents are as follows:
s201, smoothing the image by using a 3 x 3 Gaussian filter, filtering noise, reducing the sensitivity of a detector to the noise, and using a normally distributed Gaussian kernel
Performing convolution operation with each pixel point on the image, wherein each pixel value is set as the weighted average of its neighboring pixels:
the H matrix is a Gaussian kernel matrix after normalization processing, and the A matrix is a pixel matrix formed by each pixel point on the image.
S202, using Sobel operator along x-axis and y-axis (S)x,Sy) Calculating the gradient strength and direction of each pixel point in the image, and judging whether the edge is horizontal, vertical or diagonal:
s203, applying non-maximum suppression to make the boundary thin and sharpen the edge part at the same time, eliminating the spurious response brought by the edge detection algorithm, wherein the judgment standard is that for each pixel, if the pixel is the local maximum M (x, y) in the previously calculated gradient direction, the value is retained, otherwise, the pixel value is zeroed and suppressed by the maximum, and the specific judgment rule is as shown in formula (7):
s203, after the step (3), in the retained values, determining whether the strong pixel points are located in the final graph of the edge, determining the real and potential edges by applying double-threshold detection, setting two thresholds minVal and maxVal according to experience, and adopting the judgment standard as follows: any pixel with an intensity gradient above maxVal is an edge, any pixel with an intensity gradient below minVal is not an edge and is discarded, pixels with an intensity gradient between minVal and maxVal are considered to be an edge only if they are connected to pixels with an intensity gradient above maxVal, and edge detection is finally done by suppressing isolated weak edges, as shown in fig. 7 and 8.
S204, selecting a horizontal straight line from the target edge detected according to the algorithm as the real-time height of the liquid level, dynamically judging every 5 minutes according to the processing speed of the current processor in order to avoid the influence of the label on the surface of the liquid medicine, judging the target edge as the label edge if the straight line is not changed in all frames in the period of time, and marking the liquid medicine plane if the straight line is dynamically changed;
s205, for the liquid level of the target infusion bottle (bag) detected by the design, because the target position may have a certain angle deviation with the camera to influence the subsequent liquid level detection, the obtained picture needs to be horizontally rotated and aligned as shown in FIG. 9, so that the reminding threshold value and the closing threshold value cannot be triggered prematurely, and the corrected intermediate value is selected as the liquid level of the liquid medicine.
S3, judging whether the height of the liquid medicine is lower than a preset reminding threshold value, if so, judging whether the patient needs to change the medicine or pull the needle according to the information of the patient in the hospital system, and reminding the patient and informing a nurse to change the medicine or pull the needle; the voice reminding can be carried out on patients, and the notification can be carried out on nurses through a display screen and a calling device of a nurse station.
S4, judging whether the height of the liquid medicine is lower than a preset closing threshold value, and if the height of the liquid medicine is lower than the preset closing threshold value, closing the liquid transfusion tube by triggering a liquid transfusion tube closing device; the closing threshold is lower than the reminding threshold, and the closing threshold and the reminding threshold can be set to be at the upper and lower positions of the bottleneck of the infusion bottle (bag). The infusion tube closing device is clamped on the infusion tube through an omega-shaped through hole arranged on the device, and the infusion tube closing device clamps the infusion tube after receiving a closing signal.
Compared with the existing infusion monitoring method, the method can monitor the liquid medicine amount in the infusion bottle (bag) in real time, and the camera does not have any influence on the liquid medicine; the monitoring of the amount of liquid in the infusion bottle (bag) is higher in accuracy and more accurate in detection relative to the detection of the liquid, and can remind a patient and inform a nurse more timely. When the nurse is informed, the nurse is also informed that the patient needs to pull out the needle or change the medicine, so that the workload of the nurse is reduced, and when the liquid medicine in the infusion bottles (bags) of a plurality of patients needs to be infused, the nurse can determine the next working sequence according to the specific condition of each patient, namely whether the patient needs to pull out the needle or change the medicine. And the setting of the reminding threshold, the closing threshold and the closing device of the infusion tube can effectively help nurses to deal with the situation that the infusion of the liquid medicine in the infusion bottles (bags) of a plurality of patients is finished when the work is busy. The nurse is informed to the liquid medicine height is less than the predetermined warning threshold value, if the nurse is busy, can not in time pull out the needle or change dressings for patient, and the liquid medicine in infusion bottle (bag) continues the afterflow to when reacing the predetermined threshold value of closing, trigger transfer line closing means and close the transfer line, let the liquid in the transfer line no longer flow, prevent that the liquid medicine from transporting to the end, avoid causing the emergence of the medical accident that air admission blood vessel or blood refluence caused.
The foregoing is merely an example of the present invention and common general knowledge of known specific structures and features of the embodiments is not described herein in any greater detail. It should be noted that, for those skilled in the art, without departing from the structure of the present invention, several changes and modifications can be made, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicability of the patent. The scope of the claims of the present application shall be determined by the contents of the claims, and the description of the embodiments and the like in the specification shall be used to explain the contents of the claims.
Claims (8)
1. An infusion monitoring system, characterized in that: the infusion tube closing device comprises a camera device, a server, a reminding device and an infusion tube closing device, wherein the server comprises a detection module, a judgment module and a data storage module;
the camera device is used for monitoring the infusion bottle and sending the video image to the detection module;
the detection module is used for detecting a target infusion bottle in the video image by adopting a neural network model and detecting the height of liquid medicine in the target infusion bottle by adopting an edge detection algorithm; the edge detection algorithm adopted by the detection module is a Canny edge detection algorithm, the edge of the target infusion bottle detected by the Canny edge detection algorithm is adopted, a horizontal straight line in the edge is selected as the real-time height of the liquid level of the medicine, dynamic judgment is carried out at intervals of preset interval time according to the processing speed of an adopted processor, if all frames in the preset interval time have dynamic change, the straight line is judged to be the edge of a label if the straight line has no dynamic change, and the straight line is judged to be the liquid level if the straight line has dynamic change and is marked;
the judging module is used for judging whether the height of the liquid medicine is lower than a preset reminding threshold value or not, if so, judging whether the patient needs to change the medicine or pull the needle according to the patient information stored in the data storage module, and triggering the reminding device;
the reminding device is used for reminding a patient and informing a nurse of changing the medicine or pulling out the needle;
the judgment module is also used for judging whether the height of the liquid medicine is lower than a preset closing threshold value or not, and if so, triggering the liquid conveying pipe closing device;
the infusion tube closing device is used for closing the infusion tube;
and the data storage module is used for storing the patient information, the reminding threshold value and the closing threshold value.
2. The infusion monitoring system of claim 1, wherein: the neural network model adopted by the detection module is a convolutional neural network, and the convolutional neural network is composed of two convolutional layers, two pooling layers and two full-connection layers.
3. The infusion monitoring system of claim 1, wherein: and if the detection module detects that a certain angle deviation exists between the position of the target infusion bottle and a camera of the camera device, the detection module performs horizontal rotation alignment processing on the picture containing the marked liquid medicine plane, and selects the middle value of the processed liquid medicine plane as the liquid medicine level.
4. The infusion monitoring system of claim 1, wherein: the infusion tube closing device is clamped on an infusion tube and comprises a shell, an omega-shaped through hole for the infusion tube to pass through is formed in the shell, a first groove is formed in the side face of the shell, a second groove is formed in the side face of the first groove, a T-shaped reset rod and a T-shaped spring rod are arranged in the first groove, a long through hole for the infusion tube to pass through is formed in the rod portion of the T-shaped reset rod, an opening for the infusion tube to be clamped into the long through hole is formed in the side of the long through hole, the head portion of the T-shaped reset rod is located outside the shell, the bottom surface of the rod portion of the T-shaped reset rod abuts against the top surface of the head portion of the T-shaped spring rod, the bottom surface of the head portion of the T-shaped spring rod is connected with one end of a first spring, the other end of the first spring is connected with the bottom surface of the first groove, and a third groove corresponding to the second groove is formed in the side surface of the head portion of the T-shaped spring rod, the T-shaped limiting rod is arranged in the second groove, the head of the T-shaped limiting rod is used for limiting the extension and retraction of the T-shaped spring rod, the bottom surface of the head of the T-shaped limiting rod is connected with the second spring, the other end of the second spring is connected with the electromagnet, the electromagnet is connected with the battery and the controller, the controller is used for controlling the electric conduction of the electromagnet, and the controller is connected with the judging module of the server.
5. An infusion monitoring method is characterized in that: the method comprises the following steps:
s1, monitoring the infusion bottle by a camera device;
s2, detecting a target infusion bottle in the video image by adopting a neural network model, and detecting the height of liquid medicine in the target infusion bottle by adopting an edge detection algorithm; s2, selecting a horizontal straight line as the real-time height of the liquid level of the medicine from the edge of the target infusion bottle detected by the Canny edge detection algorithm, dynamically judging every preset interval time according to the processing speed of an adopted processor, judging whether the straight line has dynamic change in all frames within the preset interval time, if not, judging that the straight line is the label edge, and if so, judging that the straight line is the liquid level and marking the liquid level;
s3, judging whether the height of the liquid medicine is lower than a preset reminding threshold value, if so, judging whether the patient needs to change the medicine or pull the needle according to the information of the patient in the system, and reminding the patient and informing a nurse of changing the medicine or pulling the needle;
and S4, judging whether the height of the liquid medicine is lower than a preset closing threshold value, and if the height of the liquid medicine is lower than the preset closing threshold value, triggering a closing device of the infusion tube to close the infusion tube.
6. The infusion monitoring method according to claim 5, characterized in that: the neural network model is a convolutional neural network, and the convolutional neural network is composed of two convolutional layers, two pooling layers and two full-connection layers.
7. The infusion monitoring method according to claim 5, characterized in that: if a certain angle deviation exists between the position of the target infusion bottle and a camera of the camera device, the picture containing the marked liquid medicine plane is horizontally rotated and aligned, and the middle value of the processed liquid medicine plane is selected as the liquid medicine level.
8. The infusion monitoring method according to claim 5, characterized in that: the infusion tube closing device is clamped on the infusion tube through an omega-shaped through hole arranged on the device, and the infusion tube closing device clamps the infusion tube after receiving a closing signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011623190.4A CN112642022B (en) | 2020-12-31 | 2020-12-31 | Infusion monitoring system and monitoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011623190.4A CN112642022B (en) | 2020-12-31 | 2020-12-31 | Infusion monitoring system and monitoring method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112642022A CN112642022A (en) | 2021-04-13 |
| CN112642022B true CN112642022B (en) | 2022-07-05 |
Family
ID=75366717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011623190.4A Active CN112642022B (en) | 2020-12-31 | 2020-12-31 | Infusion monitoring system and monitoring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112642022B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113491806B (en) * | 2021-09-10 | 2021-11-09 | 南通华恩医疗设备制造有限公司 | Medical data variable measurement monitoring method and system based on big data |
| CN114565848B (en) * | 2022-02-25 | 2022-12-02 | 佛山读图科技有限公司 | Liquid medicine level detection method and system in complex scene |
Family Cites Families (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2064134A1 (en) * | 1991-04-23 | 1992-10-24 | Gary A. Thill | Free flow prevention system for infusion pump |
| AU2003235627A1 (en) * | 2002-01-19 | 2003-07-30 | Pvt Probenverteiltechnik Gmbh | Method and device for the analysis of body fluids |
| JP4082079B2 (en) * | 2002-04-30 | 2008-04-30 | ソニー株式会社 | Image signal processing apparatus and method |
| US7303175B2 (en) * | 2004-07-16 | 2007-12-04 | Cardinal Health 303, Inc. | Automatic clamp apparatus having lateral motion resistance for IV infusion sets |
| JP4517826B2 (en) * | 2004-11-15 | 2010-08-04 | パナソニック電工株式会社 | Liquid level detection method |
| WO2010091313A2 (en) * | 2009-02-06 | 2010-08-12 | Zevex, Inc. | Automatic safety occluder |
| WO2011033788A1 (en) * | 2009-09-17 | 2011-03-24 | パナソニック株式会社 | Medicinal solution injection device and medicinal solution injection method |
| US20110317004A1 (en) * | 2010-06-29 | 2011-12-29 | Kai Tao | IV Monitoring by Digital Image Processing |
| US8531517B2 (en) * | 2010-07-15 | 2013-09-10 | Kai Tao | IV monitoring by video and image processing |
| CN102058916B (en) * | 2011-02-18 | 2012-08-08 | 李永林 | Externally embedded photoelectric detection drip transfusion controller |
| CN102274556B (en) * | 2011-05-12 | 2015-05-20 | 南华大学 | Wireless infusion monitoring device and wireless monitoring system |
| US9541432B2 (en) * | 2013-05-17 | 2017-01-10 | The United States Of America As Represented By The Administrator Of The U.S. Environmental Protection Agency | Flow imaging and monitoring for synchronized management of wide area drainage |
| WO2014187432A1 (en) * | 2013-05-20 | 2014-11-27 | Tao Kai | Video iv monitor |
| CN203677656U (en) * | 2014-01-13 | 2014-07-02 | 牡丹江医学院 | Intravenous drip alarm clamping stopping device |
| EP4241806A1 (en) * | 2014-08-21 | 2023-09-13 | Micrel Medical Devices S.A. | Medication infusion safety device and a medication infusion device comprising the medication safety device |
| CN204619043U (en) * | 2015-04-30 | 2015-09-09 | 王学建 | Transfusion terminates automatic clamp and closes and alarm device |
| CN104759002A (en) * | 2015-04-30 | 2015-07-08 | 王学建 | Automatic clipping and alarming device after infusion is over |
| CN104784782A (en) * | 2015-05-14 | 2015-07-22 | 遵义师范学院 | Hospital suspended bottle transfusion monitoring and alarm device |
| CN205626624U (en) * | 2016-04-07 | 2016-10-12 | 陕西华燕航空仪表有限公司 | Transfer line liquid level monitoring device |
| CN106860970B (en) * | 2017-03-27 | 2019-12-06 | 京东方科技集团股份有限公司 | Infusion speed regulator, infusion monitoring system and operation method thereof |
| CN208492857U (en) * | 2017-08-03 | 2019-02-15 | 孟俊 | A kind of band spring Automatic-clamping blocking nurse call infusion alarm |
| CN107296999A (en) * | 2017-08-08 | 2017-10-27 | 吉林师范大学 | Medical Transfusion device residual liquid quantity automatic early-warning processing platform and application method based on Internet of Things |
| CN208741658U (en) * | 2018-04-12 | 2019-04-16 | 浙江史密斯医学仪器有限公司 | Novel infusion pump Zhi Ye mechanism |
| CN108344742B (en) * | 2018-04-13 | 2020-06-05 | 太原理工大学 | Sapphire inoculation detection device and method based on multi-frame image motion information |
| CN110836706B (en) * | 2018-08-15 | 2020-11-03 | 珠海格力电器股份有限公司 | Liquid level detection method and device |
| CN110836705A (en) * | 2018-08-15 | 2020-02-25 | 珠海格力电器股份有限公司 | Liquid level video analysis method and device |
| CN109498857B (en) * | 2018-12-29 | 2020-10-16 | 刘铁楠 | Drainage monitoring system and method based on image recognition |
| CN110211093A (en) * | 2019-04-30 | 2019-09-06 | 上海工程技术大学 | A kind of water outlet control method for automatic drinking water apparatus |
| CN110101940A (en) * | 2019-05-16 | 2019-08-09 | 西北工业大学 | Infusion monitoring system based on computer vision |
| CN110287926B (en) * | 2019-06-27 | 2021-06-01 | 武汉轻工大学 | Infusion monitoring alarm method, user equipment, storage medium and device |
| CN110624157A (en) * | 2019-11-05 | 2019-12-31 | 郑佩勇 | Medical venous transfusion monitoring system |
| CN111110956A (en) * | 2019-12-27 | 2020-05-08 | 武汉大学 | Infusion automatic alarm system and method based on machine vision and FPGA |
| CN110882440A (en) * | 2020-01-03 | 2020-03-17 | 中国计量大学 | High-reliability infusion alarm device and alarm method |
| CN111353984B (en) * | 2020-02-29 | 2023-04-07 | 杭州电子科技大学 | Self-adaptive robust high-precision detection method for liquid level in gray level image |
| CN111739058B (en) * | 2020-06-03 | 2022-10-18 | 大连理工大学 | Free liquid level recognition and extraction method based on watershed algorithm of Gaussian filtering |
| CN111729152B (en) * | 2020-06-29 | 2022-04-22 | 俸桃 | Reliable infusion alarm device |
| CN111760128A (en) * | 2020-07-16 | 2020-10-13 | 杨熠熠 | Hospital infusion reminding device |
-
2020
- 2020-12-31 CN CN202011623190.4A patent/CN112642022B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112642022A (en) | 2021-04-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112642022B (en) | Infusion monitoring system and monitoring method | |
| JP7211668B2 (en) | Emission monitoring system and method based on image recognition | |
| CN108830824A (en) | Transfusion liquid facial vision detects alarm system and its detection method | |
| JP2022535562A (en) | Systems and methods for tracking surgical instruments | |
| WO2020151149A1 (en) | Microaneurysm automatic detection method, device, and computer-readable storage medium | |
| CN111863209B (en) | Colonoscopy quality assessment workstation based on image recognition | |
| CN112386765B (en) | Intelligent infusion monitoring system based on 5G | |
| CN104182984B (en) | Method and system for rapidly and automatically collecting blood vessel edge forms in dynamic ultrasonic image | |
| CN104225721A (en) | Medical non-contacting drop monitoring system | |
| CN111009297B (en) | Supervision method and device for medicine taking behaviors of user and intelligent robot | |
| CN107495971A (en) | Morbidity's alarm medical system and its detection method based on skeleton identification | |
| CN109993063A (en) | A kind of method and terminal identified to rescue personnel | |
| CN115458120A (en) | Medication monitoring system | |
| CN110097012B (en) | Fatigue detection method for monitoring eye movement parameters based on N-range image processing algorithm | |
| CN114494189A (en) | Nursing wound image recognition and detection method and device | |
| CN103577810A (en) | Intelligent nursing method | |
| CN113222988A (en) | Infusion tube liquid level identification method based on deep learning and image overdivision | |
| CN113298089A (en) | Venous transfusion liquid level detection method based on image processing | |
| CN111191499A (en) | Fall detection method and device based on minimum center line | |
| CN209625346U (en) | A kind of Chinese medicine pharmacy intelligently makes up the prescription check system | |
| CN115252962A (en) | Intelligent infusion alarm method and system based on machine vision | |
| US20210316060A1 (en) | Medical drainage monitoring method, apparatus, and system based on image recognition | |
| CN204496497U (en) | For the robot system of ward data acquisition | |
| CN117292806B (en) | Equipment data risk identification early warning system based on intelligent hospital | |
| CN113491806B (en) | Medical data variable measurement monitoring method and system based on big data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |